diff options
Diffstat (limited to 'fs/proc/generic.c')
| -rw-r--r-- | fs/proc/generic.c | 447 |
1 files changed, 329 insertions, 118 deletions
diff --git a/fs/proc/generic.c b/fs/proc/generic.c index e3cda0b5968f..501889856461 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * proc/fs/generic.c --- generic routines for the proc-fs * @@ -8,12 +9,14 @@ * Copyright (C) 1997 Theodore Ts'o */ +#include <linux/cache.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/namei.h> #include <linux/slab.h> #include <linux/printk.h> #include <linux/mount.h> @@ -23,12 +26,24 @@ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/uaccess.h> +#include <linux/seq_file.h> #include "internal.h" static DEFINE_RWLOCK(proc_subdir_lock); -static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de) +struct kmem_cache *proc_dir_entry_cache __ro_after_init; + +void pde_free(struct proc_dir_entry *pde) +{ + if (S_ISLNK(pde->mode)) + kfree(pde->data); + if (pde->name != pde->inline_name) + kfree(pde->name); + kmem_cache_free(proc_dir_entry_cache, pde); +} + +static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len) { if (len < de->namelen) return -1; @@ -60,7 +75,7 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, struct proc_dir_entry *de = rb_entry(node, struct proc_dir_entry, subdir_node); - int result = proc_match(len, name, de); + int result = proc_match(name, de, len); if (result < 0) node = node->rb_left; @@ -83,7 +98,7 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, struct proc_dir_entry *this = rb_entry(*new, struct proc_dir_entry, subdir_node); - int result = proc_match(de->namelen, de->name, this); + int result = proc_match(de->name, this, de->namelen); parent = *new; if (result < 0) @@ -100,33 +115,38 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, return true; } -static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) +static int proc_notify_change(struct mnt_idmap *idmap, + struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct proc_dir_entry *de = PDE(inode); int error; - error = setattr_prepare(dentry, iattr); + error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) return error; - setattr_copy(inode, iattr); - mark_inode_dirty(inode); + setattr_copy(&nop_mnt_idmap, inode, iattr); proc_set_user(de, inode->i_uid, inode->i_gid); de->mode = inode->i_mode; return 0; } -static int proc_getattr(const struct path *path, struct kstat *stat, +static int proc_getattr(struct mnt_idmap *idmap, + const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_dir_entry *de = PDE(inode); - if (de && de->nlink) - set_nlink(inode, de->nlink); + if (de) { + nlink_t nlink = READ_ONCE(de->nlink); + if (nlink > 0) { + set_nlink(inode, nlink); + } + } - generic_fillattr(inode, stat); + generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); return 0; } @@ -144,24 +164,15 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret, { const char *cp = name, *next; struct proc_dir_entry *de; - unsigned int len; - de = *ret; - if (!de) - de = &proc_root; - - while (1) { - next = strchr(cp, '/'); - if (!next) - break; - - len = next - cp; - de = pde_subdir_find(de, cp, len); + de = *ret ?: &proc_root; + while ((next = strchr(cp, '/')) != NULL) { + de = pde_subdir_find(de, cp, next - cp); if (!de) { WARN(1, "name '%s'\n", name); return -ENOENT; } - cp += len + 1; + cp = next + 1; } *residual = cp; *ret = de; @@ -191,8 +202,8 @@ int proc_alloc_inum(unsigned int *inum) { int i; - i = ida_simple_get(&proc_inum_ida, 0, UINT_MAX - PROC_DYNAMIC_FIRST + 1, - GFP_KERNEL); + i = ida_alloc_max(&proc_inum_ida, UINT_MAX - PROC_DYNAMIC_FIRST, + GFP_KERNEL); if (i < 0) return i; @@ -202,15 +213,36 @@ int proc_alloc_inum(unsigned int *inum) void proc_free_inum(unsigned int inum) { - ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); + ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); +} + +static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0) + return 0; /* revalidate */ + return 1; +} + +static int proc_misc_d_delete(const struct dentry *dentry) +{ + return atomic_read(&PDE(d_inode(dentry))->in_use) < 0; } +static const struct dentry_operations proc_misc_dentry_ops = { + .d_revalidate = proc_misc_d_revalidate, + .d_delete = proc_misc_d_delete, +}; + /* * Don't create negative dentries here, return -ENOENT by hand * instead. */ -struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, - struct dentry *dentry) +struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, + struct proc_dir_entry *de) { struct inode *inode; @@ -222,9 +254,11 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &simple_dentry_operations); - d_add(dentry, inode); - return NULL; + if (de->flags & PROC_ENTRY_FORCE_LOOKUP) + return d_splice_alias_ops(inode, dentry, + &proc_net_dentry_ops); + return d_splice_alias_ops(inode, dentry, + &proc_misc_dentry_ops); } read_unlock(&proc_subdir_lock); return ERR_PTR(-ENOENT); @@ -233,7 +267,12 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - return proc_lookup_de(PDE(dir), dir, dentry); + struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb); + + if (fs_info->pidonly == PROC_PIDONLY_ON) + return ERR_PTR(-ENOENT); + + return proc_lookup_de(dir, dentry, PDE(dir)); } /* @@ -245,17 +284,17 @@ struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, * value of the readdir() call, as long as it's non-negative * for success.. */ -int proc_readdir_de(struct proc_dir_entry *de, struct file *file, - struct dir_context *ctx) +int proc_readdir_de(struct file *file, struct dir_context *ctx, + struct proc_dir_entry *de) { int i; if (!dir_emit_dots(file, ctx)) return 0; + i = ctx->pos - 2; read_lock(&proc_subdir_lock); de = pde_subdir_first(de); - i = ctx->pos - 2; for (;;) { if (!de) { read_unlock(&proc_subdir_lock); @@ -276,8 +315,8 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file, pde_put(de); return 0; } - read_lock(&proc_subdir_lock); ctx->pos++; + read_lock(&proc_subdir_lock); next = pde_subdir_next(de); pde_put(de); de = next; @@ -289,8 +328,12 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file, int proc_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); + struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); + + if (fs_info->pidonly == PROC_PIDONLY_ON) + return 1; - return proc_readdir_de(PDE(inode), file, ctx); + return proc_readdir_de(file, ctx, PDE(inode)); } /* @@ -304,6 +347,17 @@ static const struct file_operations proc_dir_operations = { .iterate_shared = proc_readdir, }; +static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + /* * proc directories can do almost nothing.. */ @@ -313,13 +367,34 @@ static const struct inode_operations proc_dir_inode_operations = { .setattr = proc_notify_change, }; -static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp) +static void pde_set_flags(struct proc_dir_entry *pde) { - int ret; + const struct proc_ops *proc_ops = pde->proc_ops; - ret = proc_alloc_inum(&dp->low_ino); - if (ret) - return ret; + if (!proc_ops) + return; + + if (proc_ops->proc_flags & PROC_ENTRY_PERMANENT) + pde->flags |= PROC_ENTRY_PERMANENT; + if (proc_ops->proc_read_iter) + pde->flags |= PROC_ENTRY_proc_read_iter; +#ifdef CONFIG_COMPAT + if (proc_ops->proc_compat_ioctl) + pde->flags |= PROC_ENTRY_proc_compat_ioctl; +#endif + if (proc_ops->proc_lseek) + pde->flags |= PROC_ENTRY_proc_lseek; +} + +/* returns the registered entry, or frees dp and returns NULL on failure */ +struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, + struct proc_dir_entry *dp) +{ + if (proc_alloc_inum(&dp->low_ino)) + goto out_free_entry; + + if (!S_ISDIR(dp->mode)) + pde_set_flags(dp); write_lock(&proc_subdir_lock); dp->parent = dir; @@ -327,12 +402,17 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp WARN(1, "proc_dir_entry '%s/%s' already registered\n", dir->name, dp->name); write_unlock(&proc_subdir_lock); - proc_free_inum(dp->low_ino); - return -EEXIST; + goto out_free_inum; } + dir->nlink++; write_unlock(&proc_subdir_lock); - return 0; + return dp; +out_free_inum: + proc_free_inum(dp->low_ino); +out_free_entry: + pde_free(dp); + return NULL; } static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, @@ -352,6 +432,14 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, WARN(1, "name len %u\n", qstr.len); return NULL; } + if (qstr.len == 1 && fn[0] == '.') { + WARN(1, "name '.'\n"); + return NULL; + } + if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') { + WARN(1, "name '..'\n"); + return NULL; + } if (*parent == &proc_root && name_to_int(&qstr) != ~0U) { WARN(1, "create '/proc/%s' by hand\n", qstr.name); return NULL; @@ -361,20 +449,34 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, return NULL; } - ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL); + ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!ent) goto out; + if (qstr.len + 1 <= SIZEOF_PDE_INLINE_NAME) { + ent->name = ent->inline_name; + } else { + ent->name = kmalloc(qstr.len + 1, GFP_KERNEL); + if (!ent->name) { + pde_free(ent); + return NULL; + } + } + memcpy(ent->name, fn, qstr.len + 1); ent->namelen = qstr.len; ent->mode = mode; ent->nlink = nlink; ent->subdir = RB_ROOT; - atomic_set(&ent->count, 1); + refcount_set(&ent->refcnt, 1); spin_lock_init(&ent->pde_unload_lock); INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); + /* Revalidate everything under /proc/${pid}/net */ + if ((*parent)->flags & PROC_ENTRY_FORCE_LOOKUP) + pde_force_lookup(ent); + out: return ent; } @@ -388,17 +490,13 @@ struct proc_dir_entry *proc_symlink(const char *name, (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1); if (ent) { - ent->data = kmalloc((ent->size=strlen(dest))+1, GFP_KERNEL); + ent->size = strlen(dest); + ent->data = kmemdup(dest, ent->size + 1, GFP_KERNEL); if (ent->data) { - strcpy((char*)ent->data,dest); ent->proc_iops = &proc_link_inode_operations; - if (proc_register(parent, ent) < 0) { - kfree(ent->data); - kfree(ent); - ent = NULL; - } + ent = proc_register(parent, ent); } else { - kfree(ent); + pde_free(ent); ent = NULL; } } @@ -406,8 +504,8 @@ struct proc_dir_entry *proc_symlink(const char *name, } EXPORT_SYMBOL(proc_symlink); -struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, - struct proc_dir_entry *parent, void *data) +struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode, + struct proc_dir_entry *parent, void *data, bool force_lookup) { struct proc_dir_entry *ent; @@ -417,17 +515,22 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent = __proc_create(&parent, name, S_IFDIR | mode, 2); if (ent) { ent->data = data; - ent->proc_fops = &proc_dir_operations; + ent->proc_dir_ops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; - parent->nlink++; - if (proc_register(parent, ent) < 0) { - kfree(ent); - parent->nlink--; - ent = NULL; + if (force_lookup) { + pde_force_lookup(ent); } + ent = proc_register(parent, ent); } return ent; } +EXPORT_SYMBOL_GPL(_proc_mkdir); + +struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, void *data) +{ + return _proc_mkdir(name, mode, parent, data, false); +} EXPORT_SYMBOL_GPL(proc_mkdir_data); struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, @@ -452,53 +555,128 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent = __proc_create(&parent, name, mode, 2); if (ent) { ent->data = NULL; - ent->proc_fops = NULL; + ent->proc_dir_ops = NULL; ent->proc_iops = NULL; - parent->nlink++; - if (proc_register(parent, ent) < 0) { - kfree(ent); - parent->nlink--; - ent = NULL; - } + ent = proc_register(parent, ent); } return ent; } EXPORT_SYMBOL(proc_create_mount_point); -struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, - struct proc_dir_entry *parent, - const struct file_operations *proc_fops, - void *data) +struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, + struct proc_dir_entry **parent, void *data) { - struct proc_dir_entry *pde; + struct proc_dir_entry *p; + if ((mode & S_IFMT) == 0) mode |= S_IFREG; - - if (!S_ISREG(mode)) { - WARN_ON(1); /* use proc_mkdir() */ + if ((mode & S_IALLUGO) == 0) + mode |= S_IRUGO; + if (WARN_ON_ONCE(!S_ISREG(mode))) return NULL; + + p = __proc_create(parent, name, mode, 1); + if (p) { + p->proc_iops = &proc_file_inode_operations; + p->data = data; } + return p; +} - BUG_ON(proc_fops == NULL); +struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, + const struct proc_ops *proc_ops, void *data) +{ + struct proc_dir_entry *p; - if ((mode & S_IALLUGO) == 0) - mode |= S_IRUGO; - pde = __proc_create(&parent, name, mode, 1); - if (!pde) - goto out; - pde->proc_fops = proc_fops; - pde->data = data; - pde->proc_iops = &proc_file_inode_operations; - if (proc_register(parent, pde) < 0) - goto out_free; - return pde; -out_free: - kfree(pde); -out: - return NULL; + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_ops = proc_ops; + return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_data); +struct proc_dir_entry *proc_create(const char *name, umode_t mode, + struct proc_dir_entry *parent, + const struct proc_ops *proc_ops) +{ + return proc_create_data(name, mode, parent, proc_ops, NULL); +} +EXPORT_SYMBOL(proc_create); + +static int proc_seq_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *de = PDE(inode); + + if (de->state_size) + return seq_open_private(file, de->seq_ops, de->state_size); + return seq_open(file, de->seq_ops); +} + +static int proc_seq_release(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *de = PDE(inode); + + if (de->state_size) + return seq_release_private(inode, file); + return seq_release(inode, file); +} + +static const struct proc_ops proc_seq_ops = { + /* not permanent -- can call into arbitrary seq_operations */ + .proc_open = proc_seq_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = proc_seq_release, +}; + +struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, + struct proc_dir_entry *parent, const struct seq_operations *ops, + unsigned int state_size, void *data) +{ + struct proc_dir_entry *p; + + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_ops = &proc_seq_ops; + p->seq_ops = ops; + p->state_size = state_size; + return proc_register(parent, p); +} +EXPORT_SYMBOL(proc_create_seq_private); + +static int proc_single_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *de = PDE(inode); + + return single_open(file, de->single_show, de->data); +} + +static const struct proc_ops proc_single_ops = { + /* not permanent -- can call into arbitrary ->single_show */ + .proc_open = proc_single_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, + int (*show)(struct seq_file *, void *), void *data) +{ + struct proc_dir_entry *p; + + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_ops = &proc_single_ops; + p->single_show = show; + return proc_register(parent, p); +} +EXPORT_SYMBOL(proc_create_single_data); + void proc_set_size(struct proc_dir_entry *de, loff_t size) { de->size = size; @@ -512,19 +690,18 @@ void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) } EXPORT_SYMBOL(proc_set_user); -static void free_proc_entry(struct proc_dir_entry *de) +void pde_put(struct proc_dir_entry *pde) { - proc_free_inum(de->low_ino); - - if (S_ISLNK(de->mode)) - kfree(de->data); - kfree(de); + if (refcount_dec_and_test(&pde->refcnt)) { + proc_free_inum(pde->low_ino); + pde_free(pde); + } } -void pde_put(struct proc_dir_entry *pde) +static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent) { - if (atomic_dec_and_test(&pde->count)) - free_proc_entry(pde); + rb_erase(&pde->subdir_node, &parent->subdir); + RB_CLEAR_NODE(&pde->subdir_node); } /* @@ -544,8 +721,16 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) len = strlen(fn); de = pde_subdir_find(parent, fn, len); - if (de) - rb_erase(&de->subdir_node, &parent->subdir); + if (de) { + if (unlikely(pde_is_permanent(de))) { + WARN(1, "removing permanent /proc entry '%s'", de->name); + de = NULL; + } else { + pde_erase(de, parent); + if (S_ISDIR(de->mode)) + parent->nlink--; + } + } write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); @@ -554,9 +739,6 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) proc_entry_rundown(de); - if (S_ISDIR(de->mode)) - parent->nlink--; - de->nlink = 0; WARN(pde_subdir_first(de), "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n", __func__, de->parent->name, de->name, pde_subdir_first(de)->name); @@ -582,23 +764,34 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) write_unlock(&proc_subdir_lock); return -ENOENT; } - rb_erase(&root->subdir_node, &parent->subdir); + if (unlikely(pde_is_permanent(root))) { + write_unlock(&proc_subdir_lock); + WARN(1, "removing permanent /proc entry '%s/%s'", + root->parent->name, root->name); + return -EINVAL; + } + pde_erase(root, parent); de = root; while (1) { next = pde_subdir_first(de); if (next) { - rb_erase(&next->subdir_node, &de->subdir); + if (unlikely(pde_is_permanent(next))) { + write_unlock(&proc_subdir_lock); + WARN(1, "removing permanent /proc entry '%s/%s'", + next->parent->name, next->name); + return -EINVAL; + } + pde_erase(next, de); de = next; continue; } - write_unlock(&proc_subdir_lock); - - proc_entry_rundown(de); next = de->parent; if (S_ISDIR(de->mode)) next->nlink--; - de->nlink = 0; + write_unlock(&proc_subdir_lock); + + proc_entry_rundown(de); if (de == root) break; pde_put(de); @@ -625,8 +818,26 @@ void proc_remove(struct proc_dir_entry *de) } EXPORT_SYMBOL(proc_remove); -void *PDE_DATA(const struct inode *inode) +/* + * Pull a user buffer into memory and pass it to the file's write handler if + * one is supplied. The ->write() method is permitted to modify the + * kernel-side buffer. + */ +ssize_t proc_simple_write(struct file *f, const char __user *ubuf, size_t size, + loff_t *_pos) { - return __PDE_DATA(inode); + struct proc_dir_entry *pde = PDE(file_inode(f)); + char *buf; + int ret; + + if (!pde->write) + return -EACCES; + if (size == 0 || size > PAGE_SIZE - 1) + return -EINVAL; + buf = memdup_user_nul(ubuf, size); + if (IS_ERR(buf)) + return PTR_ERR(buf); + ret = pde->write(f, buf, size); + kfree(buf); + return ret == 0 ? size : ret; } -EXPORT_SYMBOL(PDE_DATA); |